Knowerage
@MTimma
About Knowerage
Local MCP server that allows your agent to track documentation coverage over code repository.
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"knowerage": {
"command": "npx",
"args": [
"@mtimma/knowerage"
],
"env": {
"KNOWERAGE_WORKSPACE_ROOT": "${workspaceFolder}",
"KNOWERAGE_AUTO_FULL_RECONCILE": "true"
}
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Knowerage?
Knowerage is an MCP server that manages AI analysis coverage of a codebase. It tracks which files and line ranges have been analysed by an AI assistant, storing results as markdown documents and a registry. It is intended for developers using AI coding assistants who want to measure and manage what parts of their project have been covered.
How to use Knowerage?
Register the server in your MCP host configuration using npx @mtimma/knowerage and set the KNOWERAGE_WORKSPACE_ROOT environment variable to your project root. Once configured, you talk to your AI assistant in normal sentences—for example, “analyse the logical algorithm workflow in main.java” or “what part of this codebase is not yet analysed?”. The assistant creates or updates analysis documents under knowerage/analysis/ and records coverage in knowerage/registry.json.
Key features of Knowerage
- Create or update analysis documents with YAML frontmatter
- Reconcile analysis records for freshness (SHA‑256 hash based)
- Query file status: analysed vs. missing line ranges
- List stale or problematic registry records
- Export a coverage snapshot (JSON, YAML, TXT, or HTML)
- Generate a bundled export of selected analyses
Use cases of Knowerage
- Analyse a specific file, class, or algorithm and record the result
- Get an overall coverage percentage for a project
- Identify which parts of a codebase are not yet analysed
- Export a coverage report for auditing or sharing
- Detect stale analysis documents after source code changes
FAQ from Knowerage
What are the runtime requirements for Knowerage?
Node.js 18 or newer is required, and npx must be on your PATH.
How do I enable automatic file watching?
Set the environment variable KNOWERAGE_AUTO_FULL_RECONCILE to a truthy value (1, true, yes, or on). The server then watches the knowerage/ directory and runs a short debounced full reconciliation on filesystem changes.
How does Knowerage avoid infinite loops from registry writes?
The file watcher ignores writes to registry.json, so saving the registry does not trigger another reconciliation.
Where does Knowerage store analysis data?
All analysis markdown files live under knowerage/analysis/, and the coverage registry is stored at knowerage/registry.json in the project root.
What security measures does Knowerage implement?
All file paths are validated against the workspace root; path traversal (..) is rejected. Registry writes use atomic file operations for crash safety. No secrets are stored in analysis files or reports.
More Other MCP servers
Blender
ahujasidOpen-source MCP to use Blender with any LLM
Codelf
unbugA search tool helps dev to solve the naming things problem.
Servers
modelcontextprotocolModel Context Protocol Servers
Mcp
browsermcpBrowser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser
MCP Go 🚀
mark3labsA Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.
Comments